© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15822
    Prev
    Next
    INDEX
    Explanations

    for possessive pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0
    -1.02
    =
    -1.01
    seek
    -0.98
    々木
    -0.96
    +='
    -0.95
     многих
    -0.93
    *
    -0.92
    -
    -0.92
    //
    -0.89
    !
    -0.88
    POSITIVE LOGITS
     their
    1.05
     our
    1.04
     his
    1.03
    områ
    1.02
     conseguenze
    1.01
    菹
    0.99
     októ
    0.98
     asesino
    0.98
    kız
    0.98
    vät
    0.97
    Activations Density 0.075%

    No Known Activations